The speed submission to DIHARD II: Contributions and lessons learned

Sahidullah, Md; Patino, Jose; Cornell, Samuele; Yin, Ruiqing; Sivasankaran, Sunit; Bredin, Hervé; Korshunov, Pavel; Brutti, Alessio; Serizel, Romain; Vincent, Emmanuel; Evans, Nicholas: Marcel, Sébastien ; Squartini, Stefano; Barras, Claude
Idiap-RR-14-2019, Idiap Research Report, November 2019

This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, which considerably outperformed the challenge baselines, we also focus on the lessons learned from numerous approaches that we tried for single and multi-channel systems. We present several components of our diarization system, including categorization of domains, speech enhancement, speech activity detection, speaker embeddings, clustering methods, resegmentation, and system fusion. We analyze and discuss the effect of each such component on the overall diarization performance within the realistic settings of the challenge.


HAL
Type:
Report
Date:
2019-11-06
Department:
Digital Security
Eurecom Ref:
6106
Copyright:
Idiap

PERMALINK : https://www.eurecom.fr/publication/6106